Metraipolis › archive › dc_53b8d93fbfd4

Sharp and Adaptive Cluster Recovery in Slowly Mixing Gaussian Hidden Markov Models — arXiv:2610.09123

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09123
License (as archived)
CC0-1.0
Archived
2026-10-08T12:40:14.450Z
SHA-256 of the archived text
b7d18bd51491ccb8d770003ccf5c949254f1ea0e2365acb80df6a693980bf362
Stable URL of this page
https://metraipolis.com/documento/dc_53b8d93fbfd4

How to cite

Sharp and Adaptive Cluster Recovery in Slowly Mixing Gaussian Hidden Markov Models — arXiv:2610.09123 — arXiv (en), https://arxiv.org/abs/2610.09123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53b8d93fbfd4 (Metraipolis archive dc_53b8d93fbfd4, sha256 b7d18bd51491ccb8d770003ccf5c949254f1ea0e2365acb80df6a693980bf362)
BibTeX
@misc{dc53b8d93fbfd4,
  title = {Sharp and Adaptive Cluster Recovery in Slowly Mixing Gaussian Hidden Markov Models — arXiv:2610.09123},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09123},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53b8d93fbfd4; sha256 b7d18bd51491ccb8d770003ccf5c949254f1ea0e2365acb80df6a693980bf362},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study cluster recovery in a two-state Gaussian hidden Markov model in the slowly mixing regime, where the transition probability $\delta$ may vanish with the sample size. Temporal persistence creates long homogeneous segments and fundamentally changes the recovery problem relative to the i.i.d. Gaussian mixture benchmark. Rather than being purely adverse, label dependence provides exploitable structure: the statistical difficulty becomes concentrated near the rare transition points, giving rise to recovery regimes governed explicitly by their frequency $\delta$. We first characterize, up to universal constants, the oracle Bayes risk for offline and online clustering. Both problems exhibit a nonstandard polynomial risk regime, but the sequential constraint induces an additional logarithmic localization cost, yielding a genuine online/offline gap. We also study fixed lag prediction with delayed label feedback and identify the effective memory horizon beyond which past labels no longer improve the optimal rate. When the signal direction is unknown and possibly high dimensional, the problem is governed by the effective signal strength \[ r_n^2 = \frac{\|\theta\|^4/\sigma^4} {\|\theta\|^2/\sigma^2+d/n}. \] We derive minimax lower bounds and construct fully adaptive polynomial time procedures attaining the sharp recovery rates. In particular, almost full recovery is possible precisely when $r_n^2\gg\delta$. If $n\delta\gtrsim\log n$, adaptation to both the signal $\theta$ and the transition probability $\delta$ incurs no first order loss, and the sharp exact recovery threshold (under the Hamming loss) is \[ r_n^2 = 2\log(n\delta)\,(1+o(1)). \] Thus the effective complexity of the problem is governed by the number of latent transitions, rather than by the sample size itself.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ME, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2610.09123 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:15:15.341Z dalla pagina https://arxiv.org/list/stat.ME/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).